Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 1917
    Prev
    Next
    INDEX
    Explanations

    names or specific terms marked by the pattern "Ċ" and potentially related numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to legal cases or investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.96
     dismant
    -0.75
     helicop
    -0.71
     terminating
    -0.70
     acknow
    -0.68
     Jagu
    -0.67
     abolish
    -0.66
     scrap
    -0.66
     favoured
    -0.65
     agre
    -0.65
    POSITIVE LOGITS
    Enlarge
    0.91
    Joined
    0.86
    Offline
    0.84
    Updated
    0.84
    Temperature
    0.84
    PRESS
    0.82
    Definition
    0.81
    Posted
    0.79
    Legendary
    0.79
    Reviewed
    0.78
    Activations Density 0.176%

    No Known Activations